top of page
Shapes and Shades

Foundations of Behavioural Data Science for Business

Behavioral Data Science is a new, emerging, interdisciplinary field, which combines techniques from the behavioural sciences, such as psychology, economics, sociology, and business, with computational approaches from computer science, statistics, data-centric engineering, information systems research and mathematics, all in order to better model, understand and predict behaviour in practice. This field emerges as a direct response to the need for studying behaviour “in the wild”, outside of ideal laboratory settings and controlled environments. Behavioral Data Science lies at the interface of all these disciplines (and a growing list of others) – all interested in combining deep knowledge about the questions underlying human, algorithmic, and systems behaviour with increasing quantities of data.


The kinds of questions this field engages are not only exciting and challenging, but also timely, such as: How can people’s wellbeing at scale be measured and improved using behavioural data science? How can we improve the entire supply chain in creative industries and produce movies, which viewers really want to see? How can we better understand machine behaviour and algorithmic behaviour? How can we better model social systems by mapping risk through time? How can we design and deliver personalised services ethically and responsibly? Behavioral Data Science is capable of addressing all these issues (and many more) partly because of the availability of new data sources and partly due to the emergence of new (hybrid) models, which merge behavioural science and data science models.


The main advantage of these models is that they expand machine learning techniques that are otherwise black boxes, making machine learning models transparent, tractable and explainable. For example, while a deep learning model can generate accurate prediction of why people select one coffee shop over the other, it will not tell you what exactly drives people’s preferences; whereas hybrid models, such as anthropomorphic learning, will be able to provide this insight.

The Foundations of Behavioural Data Science Course provides an introduction to these models illustrating the behavioural methodology with case studies from Finance and FinTech industry.

Assessment:  At the end of the course you need to complete an online test. You can do it in your own time by the specified deadline. The test is multiple choice and you need to get at least 75% of questions right to pass. Additionally, throughout the course you will be working on your Behavioural Data Science Cookbook. To pass, you would also need to submit your cookbook (your online test will have a field, where you would be able to upload your cookbook).

Download the cookbook template HERE

Cookbook in the PDF Format is available HERE

Image by ThisisEngineering RAEng

Day 1

What Is Behavioural Data Science?

In this part of the course, we will define Behavioural Data Science, look at its main strands and discuss why Behavioural Data Science is a good idea for Finance, FinTech, and other business applications.

Slides - Day 1

Group Task: Consider your own recent customer experience when you used financial services. Provide (1) one example, when you were impressed with how your service provider used your data to better serve you and (2) one example, when you were unimpressed with how your service provider used your data. Explain why you were impressed in (1) and unimpressed in (2). Why do you think this happened?

Recommended readings:

Useful video:

If you want to learn more:

Day 2

Data and Data Storytelling

In this part of the course, we will discuss the data and problems associated with behavioural data in organisations. How do we turn data into effective data storytelling, which can help us solve business problems?

Slides - Day 2

Group Task: Download the Excel file: Task 1
The data represent the demand for 20 types of credit cards offered by a financial institution. Using the data – try to produce a visual and tell a story. What do these data tell us? What is a business insight here? What advice can you provide to the company?

Recommended readings:

Image by Tanner Boriack
Image by Matthew Henry

Day 3

Human Behaviour

In this part of the course, we will provide introduction to types of human behaviour. We will discuss human predictability and human bias. We will talk about digital nudges and complexity behind their use. We will also think about how to best understand  and predict customer behaviour using behavioural data science.

Slides - Day 3

Group Task: Use the Hypothesis-driven Table, the Periodic Table and the “No Need to Fly” project description to answer the following questions:

  • What behavioural methodology underpinned “No Need to Fly”?

  • In your opinion, was there anything that the project could have done better?




Recommended reading:

If you want to learn more:

Day 4

Algorithmic Behaviour

In this part of the course, we will prove introduction to types of algorithmic behaviour. We will discuss bots and algorithms used in business. We will also address the practical understanding of algorithmic bias and how to work with it using behavioural data science.

Homework: Detect Fakes Test

Slides - Day 4


  • Import provided text into the sentiment analysis tool: what can you conclude?

  • Use provided text to generate a word cloud

  • Import 3-5 “major” terms identified by your word cloud into marcoscope tool: what can you conclude?

  • How do macroscope results compare with your sentiment analysis results?


Suggested text (you may use your own):


Video (please, watch in your own time)::


Humanyze Employee Survellance

Recommended reading:

If you want to learn more:

Image by Possessed Photography
Image by Dennis Kummer

Day 5

Systems Behaviour 

In this part, we will talk about understanding and measuring systems and culture using behavioural data science. We will also talk about predicting systems behaviour using behavioural data science.

Slides-Day 5

Group Task:


(1) Nominate one person in your group working on a personal machine (this person will be working on the chatbot and sharing his/her/their screen). 

(2) Ask a nominated group member to go to and create a FREE account

(3) Create a new "Answer Bot".

(4) Use the Training Text file to train your bot. Feel free to add your own questions/answers. You can add up to 10 questions.

Training text file is also available in the PDF format HERE.

(5) Preview your bot.

We will discuss:

  • What challenges did you encounter creating your bot?

  • What did you learn from the experience?

Recommended readings:

bottom of page